🤖 AI Summary
Existing AI-driven product design systems largely overlook internal consumer preference data and fail to effectively integrate heterogeneous external data (e.g., social media content). Method: This paper proposes a data-driven automated design framework featuring a novel preference-aware continuous conditional Generative Adversarial Network (CcGAN) jointly optimized with a dedicated preference predictor—enabling semi-supervised learning and cold-start adaptation. The framework unifies multi-source heterogeneous data (internal behavioral logs + external user-generated content) into consumer-aligned latent representations for design generation. Results: Empirical evaluation on a photography chain brand demonstrates superior template quality; cross-scenario network experiments confirm robust generalization, significant efficiency gains in design iteration, and higher user acceptance. Core contribution: First introduction of a differentiable, preference-controllable CcGAN architecture that eliminates reliance on extensive labeled data or domain-specific design priors.
📝 Abstract
The rise of generative artificial intelligence (AI) has facilitated automated product design but often neglects valuable consumer preference data within companies' internal datasets. Additionally, external sources such as social media and user-generated content (UGC) platforms contain substantial untapped information on product design and consumer preferences, yet remain underutilized. We propose a novel framework that transforms the product design paradigm to be data-driven, automated, and consumer-centric. Our method employs a semi-supervised deep generative architecture that systematically integrates multidimensional consumer preferences and heterogeneous external data. The framework is both generative and preference-aware, enabling companies to produce consumer-aligned designs with enhanced cost efficiency. Our framework trains a specialized predictor model to comprehend consumer preferences and utilizes predicted popularity metrics to guide a continuous conditional generative adversarial network (CcGAN). The trained CcGAN can directionally generate consumer-preferred designs, circumventing the expenditure associated with testing suboptimal candidates. Using external data, our framework offers particular advantages for start-ups or other resource-constrained companies confronting the ``cold-start"problem. We demonstrate the framework's efficacy through an empirical application with a self-operated photography chain, where our model successfully generated superior photo template designs. We also conduct web-based experiments to verify our method and confirm its effectiveness across varying design contexts.